Expanded Parts Model for Human Attribute and Action Recognition in Still Images
Authors:
- Gaurav SharmaGSGaurav Sharma
- Frederic JurieFJFrederic Jurie
- Cordelia SchmidCSCordelia Schmid
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 652-659
Abstract
We propose a new model for recognizing human attributes (e.g. wearing a suit, sitting, short hair) and actions (e.g. running, riding a horse) in still images. The proposed model relies on a collection of part templates which are learnt discriminatively to explain specific scale-space locations in the images (in human centric coordinates). It avoids the limitations of highly structured models, which consist of a few (i.e. a mixture of) 'average' templates. To learn our model, we propose an algorithm which automatically mines out parts and learns corresponding discriminative templates with their respective locations from a large number of candidate parts. We validate the method on recent challenging datasets: (i) Willow 7 actions [7], (ii) 27 Human Attributes (HAT) [25], and (iii) Stanford 40 actions [37]. We obtain convincing qualitative and state-of-the-art quantitative results on the three datasets.Keywords
This publication has 27 references indexed in Scilit:
- Human action recognition by learning bases of action attributes and parts2011
- Articulated pose estimation with flexible mixtures-of-parts2011
- Modeling mutual context of object and human pose in human-object interaction activities2010
- Grouplet: A structured image representation for recognizing human and object interactions2010
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Observing Human-Object Interactions: Using Spatial and Functional Compatibility for RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- Weakly Supervised Scale-Invariant Learning of Models for Visual RecognitionInternational Journal of Computer Vision, 2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004